Big data cleaning method based on deep learning and data feature matching

Abstract

The invention relates to the technical field of data cleaning processing, in particular to a big data cleaning method based on deep learning and data feature matching, and the method comprises the following steps: constructing a three-dimensional electromagnetic pollution topological map through an electromagnetic fingerprint spectrum generator; anti-interference cleaning channels are activated according to dynamic changes of the electromagnetic pollution topological map, and each channel generates a channel configuration instruction set; receiving a channel configuration instruction set, executing dual operations of data pulse waveform reconstruction and feature restoration, and outputting a restored clean data block; and writing back the clean data block to the original storage medium. According to the method, accurate recovery of pulse distortion caused by electromagnetic interference is achieved, and compared with a traditional method based on low-pass filtering or interpolation recovery, nonlinear interference components can be more effectively removed, data signal integrity is ensured, and the fidelity of recovered data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data cleaning processing, and in particular to a big data cleaning method based on deep learning and data feature matching. Background Art

[0002] In the field of modern information storage and communication, data integrity and reliability face many complex challenges. Especially in high-noise electromagnetic environments, unstable storage media and high-speed data interaction scenarios, traditional data cleaning and error correction methods often cannot ensure accurate data recovery and long-term availability.

[0003] At present, the mainstream data processing methods for electromagnetic interference and storage medium noise mainly include low-pass filtering, interpolation reconstruction, error correction (ECC), data redundancy storage (RAID), etc., but these methods have obvious limitations in practical applications: traditional low-pass filtering or interpolation algorithms are difficult to effectively remove high-frequency nonlinear interference, resulting in signal distortion and affecting data accuracy. Methods such as ECC usually rely on fixed redundant bits for error correction, but in a strong interference environment, data errors that exceed the ECC error correction capability will accumulate, eventually making the data unrecoverable. Summary of the invention

[0004] The present invention provides a big data cleaning method based on deep learning and data feature matching.

[0005] The big data cleaning method based on deep learning and data feature matching includes the following steps: S1: Real-time monitoring of the electromagnetic interference intensity distribution of the data collection environment, and construction of a three-dimensional electromagnetic pollution topology map through an electromagnetic fingerprint generator; S2: According to the dynamic changes of the electromagnetic pollution topology map, the anti-interference cleaning channel is activated, and each channel generates a channel configuration instruction set including frequency band isolation parameters, signal regeneration coefficients, and quantum annealing initial conditions; S3: receiving channel configuration instruction set, performing dual operations of data pulse waveform reconstruction and feature repair, wherein the waveform reconstruction is based on reverse compensation of residual traces of electromagnetic radiation, and the compensation parameters are dynamically adjusted by the signal regeneration coefficient. The feature repair adopts a controlled quantum annealing algorithm to eliminate implicit bit flips. The initial temperature of the annealing process is specified by the channel configuration instruction set, and the clean data block after repair is output; S4: Writing the clean data blocks back to the original storage medium.

[0006] Optionally, the S1 specifically includes: S11, multi-band electromagnetic sensor array deployment: multi-band electromagnetic sensors are distributed in the data collection area to synchronously collect time-domain and frequency-domain electromagnetic radiation signals in the environment to generate original electromagnetic fingerprint sequences; S12, spatiotemporal feature fusion coding: timestamp alignment and spatial coordinate mapping of the original electromagnetic fingerprint sequence are performed, and the spatiotemporal correlation features of electromagnetic interference are extracted through a pre-trained convolutional neural network (CNN), where the input layer of the convolutional neural network receives spectrum slice data, and the output layer generates a three-dimensional feature tensor including electromagnetic interference intensity, interference frequency, and spatial coordinates; S13, dynamic topology modeling: input the three-dimensional feature tensor into the electromagnetic fingerprint generator, model the interference propagation path between sensor nodes based on the graph neural network (GNN), and generate a three-dimensional electromagnetic pollution topology map through node embedding update. The vertices of the three-dimensional electromagnetic pollution topology map represent the electromagnetic pollution intensity values, and the edge weights represent the interference coupling coefficients of adjacent areas. According to the real-time data stream of the sensor, a sliding window mechanism is used to update the topological map. By comparing the differences in the maps of adjacent windows, resampling of abnormal areas is triggered to ensure that the map refresh rate matches the rate of change of the electromagnetic environment.

[0007] Optionally, the S2 specifically includes: S21, dynamic change detection and channel triggering: real-time monitoring of changes in the electromagnetic pollution topology map, and activation of the anti-interference cleaning channel according to the trigger conditions: Intensity mutation detection: When the electromagnetic interference intensity of a sensor changes dramatically in a short period of time and exceeds the preset change threshold, the system will identify the point as an abnormal area and trigger the cleaning channel.

[0008] Coupling anomaly detection: If the electromagnetic interference coupling degree between two sensors exceeds the set interference diffusion threshold, indicating that the interference may propagate in space, the system will take cleaning measures for this area.

[0009] Frequency conflict detection: If the main interference frequency of a sensor falls into the working frequency band of the data signal, it may affect the normality of data transmission, and the system will isolate it.

[0010] S22, frequency band isolation parameter calculation: for the activated cleaning channel, the frequency band isolation parameter is calculated: by analyzing the set of interfered sensors, the affected frequency band is determined, and then a binary parameter vector is generated. The binary parameter vector represents the frequency band that should be shielded by the current cleaning channel, ensuring that the subsequent data cleaning process is free from the influence of the interference frequency; S23, Dynamic adjustment of signal regeneration coefficient: During the cleaning process, dynamically adjust the intensity of signal compensation: The traditional long short-term memory model is used to analyze historical interference data and predict the compensation coefficient required for the current signal recovery. The long short-term memory model receives the historical interference intensity data within a predetermined time window, calculates the regeneration coefficient of the current signal, and constrains its output using an activation function. S24, setting of initial conditions for quantum annealing: setting the initial temperature of quantum annealing based on the overall interference level of the current electromagnetic environment.

[0011] Optionally, the triggering condition includes: Intensity mutation detection: When the electromagnetic interference intensity of a sensor changes dramatically in a short period of time and exceeds the intensity change threshold, it will be identified as an abnormal area and trigger the cleaning channel; Coupling anomaly detection: If the electromagnetic interference coupling between two sensors exceeds the set spatial interference diffusion threshold, it indicates that the interference is propagating in space, and cleaning measures are taken for this area; Frequency conflict detection: If the main interference frequency of a sensor falls into the working frequency band of the data signal, this area will be isolated.

[0012] Optionally, the initial temperature of the quantum annealing in S24 includes calculating the global interference entropy in the entire monitoring area, evaluating the overall complexity of the interference, and determining the initial temperature of the quantum annealing algorithm according to the size of the global interference entropy. The more complex the interference, the higher the initial temperature.

[0013] Optionally, S2 also includes instruction set packaging and transmission, packaging the frequency band isolation parameters, signal regeneration coefficients and quantum annealing initial conditions into a channel configuration instruction set, and distributing the channel configuration instruction set to the corresponding cleaning channel through a communication bus.

[0014] Optionally, the S3 specifically includes: S31, pulse waveform reverse compensation reconstruction, eliminating the influence of electromagnetic interference on the original data pulse signal, and reconstructing the signal; S32, quantum annealing feature repair, repairs the reconstructed signal at the binary logic level to eliminate hidden data damage, including converting the reconstructed signal into a binary bit sequence and constructing an optimized energy function to measure the correctness of the signal logic bit; calculating the flip energy of each bit, considering the impact of data noise, and determining the ideal logic state at the bit level; evaluating the coupling relationship between different bits through the spatiotemporal correlation coupling strength, and calculating the mutual influence strength between bits; using the quantum annealing algorithm, based on the set initial temperature, optimize the energy state of the entire bit sequence; S33, through the quantum annealing process, the optimal logic bit sequence is obtained and converted back into the repaired time domain signal.

[0015] Optionally, the S31 specifically includes collecting raw data pulse signals, and pre-extracting typical interference residual pulse templates through electromagnetic fingerprint maps; calculating the propagation delay of the interference signal, and determining the interference contribution of different sensors to the data source; dynamically adjusting the compensation amplitude through the signal regeneration coefficient, and constructing an inverse compensation model based on convolution operation to generate a compensated signal so that it is close to the ideal signal waveform in the absence of interference.

[0016] Optionally, S33 also includes dividing the repaired time domain signal into blocks according to a preset data block standard to form structured data that meets application requirements; calculating the error between the repaired data block and the ideal data block, and ensuring that the error is within a preset fault tolerance threshold, and outputting the final clean data block.

[0017] Optionally, S4 includes adopting a physical signal injection method to write the clean data block back to the original storage medium according to the physical encoding rule of the storage medium (such as the P / E cycle characteristics of the NAND flash memory).

[0018] Beneficial effects of the present invention: The present invention, through electromagnetic pollution topology modeling and dynamic cleaning channel activation mechanism, can accurately detect electromagnetic interference sources in the environment, and perform waveform reconstruction and feature repair on the affected data based on spatiotemporal feature extraction, especially pulse waveform reconstruction based on convolution inverse compensation, which can dynamically adjust the signal compensation amplitude, and combine with the interference residual template in the electromagnetic fingerprint spectrum to achieve accurate recovery of pulse distortion caused by electromagnetic interference. Compared with traditional methods based on low-pass filtering or interpolation repair, the present invention can more effectively remove nonlinear interference components, ensure data signal integrity, and improve the fidelity of recovered data.

[0019] The present invention adopts controlled quantum annealing feature repair technology, constructs an optimized energy function including single-point bit flip energy and spatiotemporal coupling strength, and combines storage medium characteristics and electromagnetic environment changes to achieve dynamic correction at the data logic level. Compared with the traditional error correction algorithm based on bit error rate (BER) detection, the present invention can find the optimal data bit sequence through a global optimization strategy in a high-interference environment, thereby improving the robustness of data logic recovery. In addition, the adaptive adjustment of the annealing temperature based on the global interference entropy can enhance the error correction capability for complex interference patterns in a high-noise environment, reduce the computational overhead in a low-noise environment, and optimize the computational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a cleaning method according to an embodiment of the present invention; Figure 2 A schematic diagram of generating a channel configuration instruction set according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0023] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0024] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0025] like Figure 1-Figure 2 As shown, the big data cleaning method based on deep learning and data feature matching includes the following steps: S1: Real-time monitoring of the electromagnetic interference intensity distribution of the data collection environment, and construction of a three-dimensional electromagnetic pollution topology map through an electromagnetic fingerprint generator; S2: According to the dynamic changes of the electromagnetic pollution topology map, the anti-interference cleaning channel is activated, and each channel generates a channel configuration instruction set including frequency band isolation parameters, signal regeneration coefficients, and quantum annealing initial conditions; S3: Receive channel configuration instruction set, perform dual operations of data pulse waveform reconstruction and feature repair, where waveform reconstruction is based on reverse compensation of residual traces of electromagnetic radiation, compensation parameters are dynamically adjusted by signal regeneration coefficients, and feature repair uses controlled quantum annealing algorithm to eliminate implicit bit flips (repair data features through quantum annealing algorithm, match the feature distribution of original data, and eliminate implicit errors). The initial temperature of the annealing process is specified by the channel configuration instruction set, and the clean data block after repair is output; S4: Writing the clean data blocks back to the original storage medium.

[0026] S1 specifically includes: S11, multiple multi-band electromagnetic sensors are deployed in the data collection area. (No. sensors) at time The collected electromagnetic radiation signal is represented as a frequency domain slice : ,in Indicates sensor In the The radiation intensity value of each frequency band, Indicates sensor In time Frequency domain slices of the acquisition.

[0027] S12, slice the frequency domain collected by the sensor Input the pre-trained convolutional neural network (CNN) to extract spatiotemporal features. The output of CNN is a three-dimensional feature tensor. ,in, Indicates sensor In time The electromagnetic interference intensity value, Indicates sensor In time The main interference frequency, Indicates sensor The spatial coordinates of Indicates sensor In time The generated three-dimensional feature tensor; The loss function Defined as: ,in, The frequency domain slice reconstructed by CNN, is the network weight, is the regularization coefficient.

[0028] S13, Dynamic Topology Modeling: Transforming 3D feature tensors Input electromagnetic fingerprint generator, build dynamic 3D electromagnetic pollution topology map based on graph neural network, and define graph structure , where the vertex set Represents the electromagnetic pollution state of the sensor node; the edge set represents the interference coupling relationship between nodes, Indicates sensor The edge between Indicates sensor The interference coupling coefficient between Determined by the following formula: ; in, is the attenuation coefficient of the frequency difference, represents the Euclidean distance between sensors, and the node embedding update is expressed as: ; in, Representation Node In the The embedding vector of the layer, Representation Node In the The embedding vector of the layer, Representation Node The neighbor set of For the The weight matrix of the layer, is the activation function.

[0029] Online map calibration: Use a sliding window mechanism to update the topology map, and define the window size as , the window sliding step is , for each window , calculate the difference between the graphs of adjacent windows : ,in, Representation Node In the The final embedding vector of the layer, if ( is the difference threshold), then the abnormal area is resampled, the sensor data is updated and the topology map is regenerated.

[0030] Low noise environment (stable electromagnetic environment): τ1∈[0.01,0.05] Moderate noise environment (general industrial scenario): τ1∈[0.05,0.1] High noise environment (areas with strong electromagnetic interference, such as near radar stations and wireless base stations): τ∈[0.1,0.2].

[0031] S2 specifically includes: S21, dynamic change detection and channel triggering: real-time monitoring of the vertex set V(t) and edge set E(t) of the electromagnetic pollution topology map. When any of the following conditions is met, the anti-interference cleaning channel is activated: Intensity mutation detection: If the vertex (sensor In time The electromagnetic interference intensity of the corresponding vertex satisfy , the vertex set of the electromagnetic pollution topological map and edge sets Perform real-time monitoring and activate the anti-interference cleaning channel when any of the following conditions are met: is the intensity change threshold, with a value of 0.3. is the monitoring interval; Coupling anomaly detection: If the edge The coupling coefficient satisfy ,in, is the spatial interference diffusion threshold, β∈[10 −2 ,10 −1 ]; Frequency conflict detection: If the vertex The main interference frequency (sensor In time The main interference frequency observed falls within the data signal frequency band .

[0032] S22, frequency band isolation parameter calculation: Generate frequency band isolation parameters for the activated cleaning channel , Indicates The frequency band isolation parameter vector of the cleaning channel is a binary parameter vector, where: ,in, For the A frequency band isolation parameter vector, Indicates The set of abnormal sensors associated with each channel, For the The boundary value of the frequency band, It means "existence". It means "to make", Indicates that at least one sensor exists Belongs to the set of disturbed abnormal sensors , Indicates the main interference frequency of the sensor Fall into within the frequency band.

[0033] S23, Dynamic adjustment of signal regeneration coefficient: Generate signal regeneration coefficient through pre-trained LSTM (Long Short-Term Memory Network) model , whose input is the historical interference intensity sequence , indicating obtaining The disturbance intensity history sequence of time steps, where is the input time window length of LSTM, and the output is: ,in, and For model weights and biases, the Sigmoid function constrains the output to the range [0,1]; S24, quantum annealing initial condition setting: according to the vertex set The global interference entropy Set the initial annealing temperature : ; ; in, To preset the maximum temperature, is the entropy sensitivity coefficient, taking the empirical value from 0.5 to 1.2, is the total interference strength of all sensors, is the total number of sensors.

[0034] Encapsulate the above parameters into a channel configuration instruction set ,distributed to the execution units of the corresponding cleaning channels through a low-latency bus.

[0035] S3 specifically includes: S31, pulse waveform reverse compensation reconstruction: the original data pulse signal Eliminate residual traces of electromagnetic radiation and reconstruct waveform signals It is expressed as: ; in, represents the convolution operation, is the Dirac pulse function, To interfere with the residual pulse template (pre-extracted by electromagnetic fingerprint), Indicates sensor To the data source location The propagation delay ( is the electromagnetic wave speed, which is 3.0×10 8 m / s), , is the reference interference strength benchmark value (based on hardware specification settings, generally ), is the signal regeneration coefficient, dynamically adjusts the compensation amplitude, is the spatial coordinate of the data source, Indicates the Euclidean distance between the sensor and the data source.

[0036] S32, quantum annealing feature repair: The reconstructed pulse signal Convert to binary bit sequence , is the total length of the binary bit sequence, constructing the controlled quantum annealing energy function : ; in, represents the single-point bit flip energy, ,in, is an ideal logic level, is the noise variance, represents the spatiotemporal correlation coupling strength, ,in, is the signal coherence time, ranging from 10 to 100 ms, is the set of associated bit pairs, determined by the pulse timing correlation, The first binary bit sequence Bit; Logic high level (1) value: 3.3V, 5V, 1.8V (depending on the circuit standard) Logic low level (0) value: 0V; Based on the initial temperature To perform a controlled anneal: , where the annealing temperature according to attenuation, is the annealing time constant, synchronized with the hardware clock cycle, represents the quantum annealing transition probability; S33, Clean Data Block Generation: Obtaining Optimal Bit Sequences via Quantum Annealing , convert it into the repaired time domain signal , and split into data blocks ,satisfy: ; in, is the ideal data block template, is the matrix Frobenius norm, is the optimal bit sequence after annealing optimization, After repair data blocks, Value .

[0037] The extraction of interference residual pulse template is based on electromagnetic fingerprint, as follows: Record electromagnetic radiation signals in the target area, including intensity, frequency, and time characteristics.

[0038] Perform short-time Fourier transform on the collected data to extract the time-frequency distribution characteristics of electromagnetic interference in each frequency band.

[0039] Through the established electromagnetic fingerprint database, historical interference patterns are matched and typical interference sources (power frequency noise, radio frequency interference) are identified.

[0040] High-correlation interference patterns are selected and deconvolution technology is used to restore the original interference pulse shape.

[0041] Clustering method is used to reduce the dimension of different interference templates and store them in the interference fingerprint library for use in the real-time cleaning stage.

[0042] Using physical signal injection method, clean data blocks Write back to the original storage medium according to the physical encoding rules of the storage medium (such as the P / E cycle characteristics of NAND flash memory).

[0043] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0044] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A big data cleaning method based on deep learning and data feature matching, characterized in that: The following steps are involved: S1: Real-time monitoring of the electromagnetic interference intensity distribution of the data collection environment, and construction of a three-dimensional electromagnetic pollution topology map through an electromagnetic fingerprint generator; S2: According to the dynamic changes of the electromagnetic pollution topology map, the anti-interference cleaning channel is activated, and each channel generates a channel configuration instruction set including frequency band isolation parameters, signal regeneration coefficients, and quantum annealing initial conditions; S3: receiving channel configuration instruction set, performing dual operations of data pulse waveform reconstruction and feature repair, wherein the waveform reconstruction is based on reverse compensation of residual traces of electromagnetic radiation, and the compensation parameters are dynamically adjusted by the signal regeneration coefficient. The feature repair adopts a controlled quantum annealing algorithm to eliminate implicit bit flips. The initial temperature of the annealing process is specified by the channel configuration instruction set, and the clean data block after repair is output; S4: Writing the clean data blocks back to the original storage medium.

2. The big data cleaning method based on deep learning and data feature matching according to claim 1 is characterized in that: The S1 specifically includes: S11, multi-band electromagnetic sensor array deployment: multi-band electromagnetic sensors are distributed in the data collection area to synchronously collect time-domain and frequency-domain electromagnetic radiation signals in the environment to generate original electromagnetic fingerprint sequences; S12, spatiotemporal feature fusion coding: timestamp alignment and spatial coordinate mapping of the original electromagnetic fingerprint sequence are performed, and the spatiotemporal correlation features of electromagnetic interference are extracted through a pre-trained convolutional neural network, where the input layer of the convolutional neural network receives spectrum slice data, and the output layer generates a three-dimensional feature tensor including electromagnetic interference intensity, interference frequency, and spatial coordinates; S13, dynamic topology modeling: input the three-dimensional feature tensor into the electromagnetic fingerprint generator, model the interference propagation path between sensor nodes based on the graph neural network, and generate a three-dimensional electromagnetic pollution topology map through node embedding update. The vertices of the three-dimensional electromagnetic pollution topology map represent the electromagnetic pollution intensity values, and the edge weights represent the interference coupling coefficients of adjacent areas.

3. The big data cleaning method based on deep learning and data feature matching according to claim 1 is characterized in that: The S2 specifically includes: S21, dynamic change detection and channel triggering: real-time monitoring of changes in the electromagnetic pollution topology map, and activation of the anti-interference cleaning channel according to the trigger conditions: Intensity mutation detection: When the electromagnetic interference intensity of a sensor changes dramatically in a short period of time and exceeds the preset change threshold, the system will identify the point as an abnormal area and trigger the cleaning channel; Coupling anomaly detection: If the electromagnetic interference coupling between two sensors exceeds the set interference diffusion threshold, it indicates that the interference may propagate in space, and the system will take cleaning measures for this area; Frequency conflict detection: If the main interference frequency of a sensor falls into the working frequency band of the data signal, it may affect the normality of data transmission, and the system will isolate it; S22, frequency band isolation parameter calculation: for the activated cleaning channel, the frequency band isolation parameter is calculated: by analyzing the set of interfered sensors, the affected frequency band is determined, and then a binary parameter vector is generated. The binary parameter vector represents the frequency band that should be shielded by the current cleaning channel, ensuring that the subsequent data cleaning process is free from the influence of the interference frequency; S23, Dynamic adjustment of signal regeneration coefficient: During the cleaning process, dynamically adjust the intensity of signal compensation: The traditional long short-term memory model is used to analyze historical interference data and predict the compensation coefficient required for the current signal recovery. The long short-term memory model receives the historical interference intensity data within a predetermined time window, calculates the regeneration coefficient of the current signal, and constrains its output using an activation function. S24, setting of initial conditions for quantum annealing: setting the initial temperature of quantum annealing based on the overall interference level of the current electromagnetic environment.

4. The big data cleaning method based on deep learning and data feature matching according to claim 1 is characterized in that: The trigger conditions include: Intensity mutation detection: When the electromagnetic interference intensity of a sensor changes dramatically in a short period of time and exceeds the intensity change threshold, it will be identified as an abnormal area and trigger the cleaning channel; Coupling anomaly detection: If the electromagnetic interference coupling between two sensors exceeds the set spatial interference diffusion threshold, it indicates that the interference is propagating in space, and cleaning measures are taken for this area; Frequency conflict detection: If the main interference frequency of a sensor falls into the working frequency band of the data signal, this area will be isolated.

5. The big data cleaning method based on deep learning and data feature matching according to claim 4 is characterized in that: The initial temperature of the quantum annealing in S24 includes calculating the global interference entropy in the entire monitoring area, evaluating the overall complexity of the interference, and determining the initial temperature of the quantum annealing algorithm according to the size of the global interference entropy. The more complex the interference, the higher the initial temperature.

6. The big data cleaning method based on deep learning and data feature matching according to claim 5 is characterized in that: The S2 also includes instruction set packaging and transmission, which packages the frequency band isolation parameters, signal regeneration coefficients and quantum annealing initial conditions into a channel configuration instruction set, and the channel configuration instruction set is distributed to the corresponding cleaning channel through the communication bus.

7. The big data cleaning method based on deep learning and data feature matching according to claim 1 is characterized in that: The S3 specifically includes: S31, pulse waveform reverse compensation reconstruction, eliminating the influence of electromagnetic interference on the original data pulse signal, and reconstructing the signal; S32, quantum annealing feature repair, repairs the reconstructed signal at the binary logic level to eliminate hidden data damage, including converting the reconstructed signal into a binary bit sequence and constructing an optimized energy function to measure the correctness of the signal logic bit; calculating the flip energy of each bit, considering the impact of data noise, and determining the ideal logic state at the bit level; evaluating the coupling relationship between different bits through the spatiotemporal correlation coupling strength, and calculating the mutual influence strength between bits; using the quantum annealing algorithm, based on the set initial temperature, optimize the energy state of the entire bit sequence; S33, through the quantum annealing process, obtains the optimal logic bit sequence and converts it back into the repaired time domain signal.

8. The big data cleaning method based on deep learning and data feature matching according to claim 7 is characterized in that: The S31 specifically includes collecting raw data pulse signals and pre-extracting typical interference residual pulse templates through electromagnetic fingerprints; Calculate the propagation delay of the interference signal and determine the interference contribution of different sensors to the data source; dynamically adjust the compensation amplitude through the signal regeneration coefficient, build an inverse compensation model based on convolution operation, and generate a compensated signal to make it close to the ideal signal waveform in the absence of interference.

9. The big data cleaning method based on deep learning and data feature matching according to claim 7 is characterized in that: The S33 also includes dividing the repaired time domain signal into blocks according to a preset data block standard to form structured data that meets application requirements; Calculate the error between the repaired data block and the ideal data block, ensure that the error is within the preset fault tolerance threshold, and output the final clean data block.

10. The big data cleaning method based on deep learning and data feature matching according to claim 1 is characterized in that ,The S4 includes adopting a physical signal injection method to write the clean data block back to the original storage medium according to the physical encoding rules of the storage medium.

Images